import besca as bc
import scanpy as sc
import pandas as pd
import pkg_resources
import os
The datasets that are already annotated and should be used for training. If you only use one dataset please use list of one.
adata_trains = [bc.datasets.Smillie2019_processed()]
The dataset of interest that should be annotated.
adata_pred = bc.datasets.Haber2017_processed()
adata_orig = bc.datasets.Haber2017_processed()
Define level of dblabel reference annotation
level = 4
Give your analysis a name.
analysis_name = 'auto_annot_Haber2017_with_Smillie2019_dblabel_l' + str(level)
Specify column name of celltype annotation you want to train on.
celltype_train ='dblabel_l' + str(level)
celltype_test = 'dblabel_l' + str(level)
Choose a method:
method = 'logistic_regression_elastic' # 'logistic_regression'
Specify merge method if using multiple training datasets. Needs to be either scanorama or naive.
merge = 'scanorama'
Decide if you want to use the raw format or highly variable genes. Raw increases computational time and does not necessarily improve predictions.
use_raw = False
You can choose to only consider a subset of genes from a signature set.
genes_to_use = 'all'
new_cnames = bc.tl.sig.obtain_new_label(
nomenclature_file=pkg_resources.resource_filename('besca', 'datasets/nomenclature/CellTypes_v1.tsv'),
cnames=list(adata_trains[0].obs['dblabel'].cat.categories),
reference_label='dblabel',
new_label='dblabel',
new_level=level)
new_cnames
| new_label | |
|---|---|
| CD1c-positive myeloid dendritic cell | myeloid dendritic cell |
| CD4-positive, alpha-beta memory T cell | CD4-positive, alpha-beta T cell |
| CD8-positive, alpha-beta T cell | CD8-positive, alpha-beta T cell |
| CD8-positive, alpha-beta cytokine secreting effector T cell | CD8-positive, alpha-beta T cell |
| CD141-positive myeloid dendritic cell | myeloid dendritic cell |
| HEV endothelial cell | HEV endothelial cell |
| activated CD4-positive, alpha-beta T cell | CD4-positive, alpha-beta T cell |
| brush cell | brush cell |
| endothelial cell | endothelial cell |
| enterocyte | enterocyte |
| enterocyte progenitor | enterocyte progenitor |
| enteroendocrine cell | enteroendocrine cell |
| exhausted-like CD4-positive, alpha-beta T cell | CD4-positive, alpha-beta T cell |
| fibroblast | fibroblast |
| follicular B cell | follicular B cell |
| germinal center B cell | germinal center B cell |
| glial cell | glial cell |
| goblet cell | goblet cell |
| immature enterocyte | enterocyte |
| immature goblet cell | immature goblet cell |
| inflammatory fibroblast | inflammatory fibroblast |
| inflammatory monocyte | inflammatory monocyte |
| innate lymphoid cell | innate lymphoid cell |
| macrophage | macrophage |
| mast cell | mast cell |
| microfold cell | microfold cell |
| microvascular endothelial cell | microvascular endothelial cell |
| myofibroblast cell | myofibroblast cell |
| natural killer cell | natural killer cell |
| pericyte cell | pericyte cell |
| plasma cell | plasma cell |
| proliferating B cell | proliferating B cell |
| proliferating T cell | T cell |
| proliferating monocyte | monocyte |
| proliferating transit amplifying cell | transit amplifying cell |
| regulatory T cell | regulatory T cell |
| stem cell | stem cell |
| transit amplifying cell | transit amplifying cell |
adata_trains[0].obs['dblabel_l' + str(level)] = bc.tl.sig.add_anno(adata_trains[0], new_cnames, 'new_label', 'dblabel')
new_cnames = bc.tl.sig.obtain_new_label(
nomenclature_file=pkg_resources.resource_filename('besca', 'datasets/nomenclature/CellTypes_v1.tsv'),
cnames=list(adata_pred.obs['dblabel'].cat.categories),
reference_label='dblabel',
new_label='dblabel',
new_level=level)
new_cnames
| new_label | |
|---|---|
| goblet cell | goblet cell |
| proliferating epithelial fate stem cell | epithelial fate stem cell |
| enterocyte | enterocyte |
| epithelial fate stem cell | epithelial fate stem cell |
| immature goblet cell | immature goblet cell |
| brush cell | brush cell |
| proliferating transit amplifying cell | transit amplifying cell |
| paneth cell | paneth cell |
| transit amplifying cell | transit amplifying cell |
| proliferating enterocyte progenitor | enterocyte progenitor |
| immature enterocyte | enterocyte |
| enteroendocrine cell | enteroendocrine cell |
| enterocyte progenitor | enterocyte progenitor |
adata_pred.obs['dblabel_l' + str(level)] = bc.tl.sig.add_anno(adata_pred, new_cnames, 'new_label', 'dblabel')
adata_orig.obs['dblabel_l' + str(level)] = adata_pred.obs['dblabel_l' + str(level)]
# Select epithelial subset from Smillie2019 dataset
epithelial_subset = bc.subset_adata(adata_trains[0], adata_trains[0].obs.celltype_highlevel == 'Epi', raw=False)
adata_trains[0] = epithelial_subset
# Convert mouse symbols (MGI) to human symbols (HGNC)
mousehuman_file = pkg_resources.resource_filename('besca', 'datasets/homologs/MGItoHGNC.csv')
mousehuman=pd.read_csv(mousehuman_file,sep='\t',header='infer', encoding="unicode_escape")
mousehuman.index=mousehuman['MGI']
conversion=pd.Series(data=mousehuman['HGNC'], index=mousehuman.index)
# Convert mouse symbols (MGI) to human symbols (HGNC)
adata_orig.var.rename(columns={'SYMBOL':'MGI'}, inplace=True)
adata_orig.var['SYMBOL'] = adata_orig.var['MGI'].map(lambda x: conversion.get(x, default='') if type(conversion.get(x, default='')) == str else conversion.get(x, default=None).values[0])
adata_orig.var.index = adata_orig.var.SYMBOL
adata_orig.var_names_make_unique()
adata_pred = adata_orig.copy()
This function merges training datasets, removes unwanted genes, and if scanorama is used corrects for datasets.
adata_train, adata_pred = bc.tl.auto_annot.merge_data(adata_trains, adata_pred, genes_to_use = genes_to_use, merge = merge)
merging with scanorama using scanorama rn Found 278 genes among all datasets [[0. 0.75137665] [0. 0. ]] Processing datasets (0, 1) integrating training set calculating intersection
The returned scaler is fitted on the training dataset (to zero mean and scaled to unit variance).
classifier, scaler = bc.tl.auto_annot.fit(adata_train, method, celltype_train)
[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.
max_iter reached after 89 seconds max_iter reached after 90 seconds max_iter reached after 90 seconds max_iter reached after 90 seconds max_iter reached after 92 seconds max_iter reached after 93 seconds max_iter reached after 109 seconds max_iter reached after 115 seconds max_iter reached after 112 seconds max_iter reached after 105 seconds max_iter reached after 105 seconds max_iter reached after 106 seconds max_iter reached after 107 seconds max_iter reached after 105 seconds max_iter reached after 108 seconds max_iter reached after 107 seconds max_iter reached after 106 seconds max_iter reached after 106 seconds max_iter reached after 106 seconds max_iter reached after 108 seconds max_iter reached after 106 seconds max_iter reached after 106 seconds max_iter reached after 106 seconds max_iter reached after 107 seconds max_iter reached after 103 seconds max_iter reached after 105 seconds max_iter reached after 106 seconds max_iter reached after 103 seconds max_iter reached after 104 seconds max_iter reached after 105 seconds
[Parallel(n_jobs=10)]: Done 3 out of 3 | elapsed: 17.3min finished
Use fitted model to predict celltypes in adata_pred. Prediction will be added in a new column called 'auto_annot'. Paths are needed as adata_pred will revert to its original state (all genes, no additional corrections). The threshold should be set to 0 or left out for SVM. For logisitic regression the threshold can be set.
adata_predicted = bc.tl.auto_annot.adata_predict(classifier = classifier, scaler = scaler, adata_pred = adata_pred, adata_orig = adata_orig, threshold = 0)
Write out metrics to a report file, create confusion matrices and comparative umap plots
adata_pred.obs
| CELL | CONDITION | sample_type | donor | region_x | sample | percent_mito | n_counts | n_genes | batch | ... | celltype0 | celltype1 | celltype2 | celltype3 | dblabel | barcode | region_y | cell_label | _merge | dblabel_l4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | haber_intestine_donor_M1_Duo.AAACATACAGCGGA | healthy | mouse_small_intestine_epithelial | M1 | Duo | Duo_M1 | 0.001410 | 12768.0 | 1227 | Duo | ... | epithelial cell | paneth cell | paneth cell | paneth cell | paneth cell | AAACATACAGCGGA | Jejunum | Paneth | both | paneth cell |
| 1 | haber_intestine_donor_M1_Duo.AAACATACCTTACT | healthy | mouse_small_intestine_epithelial | M1 | Duo | Duo_M1 | 0.010779 | 6583.0 | 2156 | Duo | ... | epithelial cell | enterocyte | enterocyte | enterocyte | enterocyte | AAACATACCTTACT | Jejunum | Enterocyte | both | enterocyte |
| 2 | haber_intestine_donor_M1_Duo.AAACCGTGCAGTCA | healthy | mouse_small_intestine_epithelial | M1 | Duo | Duo_M1 | 0.022508 | 2799.0 | 1362 | Duo | ... | epithelial cell | epithelial fate stem cell | proliferating epithelial fate stem cell | proliferating epithelial fate stem cell | proliferating epithelial fate stem cell | AAACCGTGCAGTCA | Jejunum | TA | both | epithelial fate stem cell |
| 3 | haber_intestine_donor_M1_Duo.AAACGCTGCAGTCA | healthy | mouse_small_intestine_epithelial | M1 | Duo | Duo_M1 | 0.015041 | 6048.0 | 2287 | Duo | ... | epithelial cell | transit amplifying cell | transit amplifying cell | transit amplifying cell | transit amplifying cell | AAACGCTGCAGTCA | Jejunum | TA | both | transit amplifying cell |
| 4 | haber_intestine_donor_M1_Duo.AAACGCTGCGTGAT | healthy | mouse_small_intestine_epithelial | M1 | Duo | Duo_M1 | 0.023022 | 2780.0 | 1320 | Duo | ... | epithelial cell | transit amplifying cell | transit amplifying cell | transit amplifying cell | transit amplifying cell | AAACGCTGCGTGAT | Jejunum | Stem | both | transit amplifying cell |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 10891 | haber_intestine_donor_M2_Il.TTTCAGTGACCAGT | healthy | mouse_small_intestine_epithelial | M2 | Il | Il_M2 | 0.008591 | 5468.0 | 2037 | Il | ... | epithelial cell | transit amplifying cell | transit amplifying cell | transit amplifying cell | transit amplifying cell | TTTCAGTGACCAGT | Ileum | EP | both | transit amplifying cell |
| 10892 | haber_intestine_donor_M2_Il.TTTCGAACAGAACA | healthy | mouse_small_intestine_epithelial | M2 | Il | Il_M2 | 0.007760 | 10174.0 | 2884 | Il | ... | epithelial cell | immature enterocyte | immature enterocyte | immature enterocyte | immature enterocyte | TTTCGAACAGAACA | Ileum | Enterocyte | both | enterocyte |
| 10893 | haber_intestine_donor_M2_Il.TTTCTACTGCTCCT | healthy | mouse_small_intestine_epithelial | M2 | Il | Il_M2 | 0.006121 | 9307.0 | 2856 | Il | ... | epithelial cell | immature goblet cell | immature goblet cell | immature goblet cell | immature goblet cell | TTTCTACTGCTCCT | Ileum | Goblet | both | immature goblet cell |
| 10894 | haber_intestine_donor_M2_Il.TTTGACTGCGCCTT | healthy | mouse_small_intestine_epithelial | M2 | Il | Il_M2 | 0.007189 | 4029.0 | 1277 | Il | ... | epithelial cell | goblet cell | goblet cell | goblet cell | goblet cell | TTTGACTGCGCCTT | Ileum | Goblet | both | goblet cell |
| 10895 | haber_intestine_donor_M2_Il.TTTGCATGGAGGAC | healthy | mouse_small_intestine_epithelial | M2 | Il | Il_M2 | 0.009316 | 8907.0 | 2277 | Il | ... | epithelial cell | enterocyte | enterocyte | enterocyte | enterocyte | TTTGCATGGAGGAC | Ileum | Enterocyte | both | enterocyte |
10896 rows × 21 columns
%matplotlib inline
bc.tl.report(
adata_pred=adata_predicted,
celltype=celltype_test,
method=method,
analysis_name=analysis_name,
train_datasets = adata_trains,
test_dataset = adata_orig,
merge = merge,
name_prediction='auto_annot',
name_report='auto_annot',
use_raw=use_raw,
remove_nonshared=True,
clustering='leiden',
asymmetric_matrix=True,
delimiter='\t',
verbose=True
)
acc: 0.39 f1: 0.31
... storing 'auto_annot' as categorical ... storing 'SYMBOL' as categorical
ami: 0.36
ari: 0.2
silhouette dblabel_l4: 0.18
silhouette auto_annot: 0.01
pair confusion matrix:
0 1
0 62649864 33562858
1 8326346 14172852
WARNING: saving figure to file figures/umap.ondata_auto_annot_Haber2017_with_Smillie2019_dblabel_l4.png
WARNING: saving figure to file figures/umap.auto_annot_Haber2017_with_Smillie2019_dblabel_l4_dblabel_l4.png
WARNING: saving figure to file figures/umap.auto_annot_Haber2017_with_Smillie2019_dblabel_l4_auto_annot.png
WARNING: saving figure to file figures/umap.auto_annot_Haber2017_with_Smillie2019_dblabel_l4_leiden.png
sc.pl.umap(adata_predicted, color=[celltype_test, 'auto_annot'])
sc.pl.umap(adata_predicted, color=[celltype_test, 'auto_annot'], legend_loc='on data', legend_fontsize=8)
sc.pl.umap(adata_predicted, color=[celltype_test, 'auto_annot'], legend_fontsize=7, wspace = 1.4, save = '.svg')
sc.pl.umap(adata_predicted, color=[celltype_test, 'auto_annot'], legend_loc='on data', legend_fontsize=7, wspace = 1.4, save = '.ondata.svg')
WARNING: saving figure to file figures/umap.svg
WARNING: saving figure to file figures/umap.ondata.svg
adata_train
View of AnnData object with n_obs × n_vars = 46102 × 278
obs: 'CELL', 'Cluster', 'Health', 'Location', 'Subject', 'celltype_highlevel', 'nGene', 'nUMI', 'original_name', 'percent_mito', 'n_counts', 'n_genes', 'batch', 'leiden', 'dblabel', 'celltype', 'cluster_celltype', 'Type', 'dblabel_l4'
var: 'SYMBOL', 'ENSEMBL-0', 'n_cells-0', 'total_counts-0', 'frac_reads-0', 'ENSEMBL-1', 'n_cells-1', 'total_counts-1', 'frac_reads-1', 'MGI-1', 'highly_variable-1', 'means-1', 'dispersions-1', 'dispersions_norm-1', 'mean-1', 'std-1'
uns: 'Cluster_colors', 'Location_colors', 'Type_colors', 'celltype_highlevel_colors', 'leiden', 'leiden_colors', 'umap'
obsm: 'X_pca', 'X_umap', 'X_scanorama'
adata_predicted_wo_unknown = adata_predicted.copy()
adata_predicted_wo_unknown = bc.subset_adata(adata_predicted_wo_unknown, adata_predicted_wo_unknown.obs.auto_annot != 'unknown', raw=False)
bc.pl.riverplot_2categories(adata_predicted_wo_unknown, [celltype_test, 'auto_annot'])
# Compare to random assignment
import random
random.seed(1)
adata_predicted.obs['random_labeling'] = list(adata_predicted.obs[celltype_test].sample(frac=1))
bc.tl.report(
adata_pred=adata_predicted,
celltype=celltype_test,
method="compare_to_random_" + method,
analysis_name=analysis_name,
train_datasets = adata_trains,
test_dataset = adata_orig,
merge = merge,
name_prediction="random_labeling",
name_report="compare_to_random_auto_annot",
use_raw=use_raw,
remove_nonshared=False,
clustering='leiden',
asymmetric_matrix=True,
delimiter='\t',
verbose=True)
acc: 0.19 f1: 0.19
... storing 'random_labeling' as categorical
ami: -0.0
ari: -0.0
silhouette dblabel_l4: 0.18
silhouette random_labeling: -0.03
pair confusion matrix:
0 1
0 77934138 18278584
1 18278584 4220614
WARNING: saving figure to file figures/umap.ondata_auto_annot_Haber2017_with_Smillie2019_dblabel_l4.png
WARNING: saving figure to file figures/umap.auto_annot_Haber2017_with_Smillie2019_dblabel_l4_dblabel_l4.png
WARNING: saving figure to file figures/umap.auto_annot_Haber2017_with_Smillie2019_dblabel_l4_random_labeling.png
WARNING: saving figure to file figures/umap.auto_annot_Haber2017_with_Smillie2019_dblabel_l4_leiden.png
from sinfo import sinfo
sinfo()
----- anndata 0.7.5 besca 2.4+57.g5ad53b2 pandas 1.2.2 pkg_resources NA plotly 4.14.3 scanpy 1.6.1 sinfo 0.3.1 sklearn 0.24.1 ----- IPython 7.20.0 jupyter_client 6.1.11 jupyter_core 4.7.1 notebook 6.2.0 ----- Python 3.7.9 | packaged by conda-forge | (default, Dec 9 2020, 21:08:20) [GCC 9.3.0] Linux-3.10.0-693.11.6.el7.x86_64-x86_64-with-centos-7.4.1708-Core 24 logical CPU cores, x86_64 ----- Session information updated at 2021-07-18 09:12
%%javascript
IPython.notebook.kernel.execute('nb_name = "' + IPython.notebook.notebook_name + '"')
nb_name = os.path.join(os.getcwd(), nb_name)
! jupyter nbconvert --to html {nb_name}
[NbConvertApp] Converting notebook /pstore/data/bioinfo/users/hatjek/devel/besca_publication_results/intestine/auto_annot/auto_annot_Haber2017_with_Smillie2019_dblabel_l4.ipynb to html [NbConvertApp] Writing 7207281 bytes to /pstore/data/bioinfo/users/hatjek/devel/besca_publication_results/intestine/auto_annot/auto_annot_Haber2017_with_Smillie2019_dblabel_l4.html